Tag Archives: variation

Lean Six Sigma

Posted on by
Reply

We don’t have control, we have choices. The best we can do is improve our method of making choices and hope for good results.

This is the rub. We generally set ourselves up for disappointment and failure because we make emotional choices and don’t get the results we want. We assume that our environment is predictable and that the universe behaves according to a fixed process that coincides nicely with our expectations. The plain truth is that you don’t know what you don’t know. And sometimes, you are not even aware that you don’t know.
This may seem like a bunch of idle chatter, but the concept impacts businesses everyday. This is why Six Sigma and Lean are so important in our global economy. Reducing variability and making processes more predictable improves the quality of our decision making. Less emotion and more critical analysis.
I did an experiment while participating in a March Madness Basketball Pool this past year. I entered three different brackets. One bracket was based upon selecting my favorite teams, one was based upon my “gut feelings” about who would win, and the last I did using statistical data from experts in the college basketball world.
These are the typical decision making strategies seen everyday in business. The emotional decision, the gut feeling, and the critically analyzed decision. In the case of my brackets, the one based on my emotions (favorite teams) fared the worst. The Bracket based upon my gut feelings did marginally better. The bracket based upon statistical research did really well.
This is the point behind Six Sigma and Lean. Moving toward data based decisions.  It doesn’t  mean that using gut feelings is always bad. There is a time and place for everything. When properly implemented, Six Sigma and Lean will reduce variation in your processes and make them more predictable. This in turn increases the quality of our choices.

Finding Sources of Variation

Posted on by
2

Typically, the most suspect processes or process steps for introducing variation are manual or judgment oriented in nature.  For example, if an individual applies personal judgment within a process you would expect to see bias or higher variation in the process output. Automated processes will typically have more consistent performance and lower variation.

One of the best ways to find these manual or judgment steps in a process is through the use of a process map. As a process is mapped, decision points are represented as diamonds. This becomes the first place to look for variation.

When mapping a process, information from both the process owners and the Six Sigma team’s observations are used. There are situations where the process as described by the process owners is really from the “as we think it is” or “as it should be” world. The Six Sigma team that falls into this trap is doomed. In these cases, the process owners may know the standardized process, but chose to not follow it.

On a project I worked a few years back, there was too much variation in the concentration of petcoke being blended with the coal burned in a business’s boilers.  The result was either too much petcoke, resulting in a violation of environmental parameters, or too little petcoke which increased the cost of operation.

The fuel feed system was comprised of 2 conveyer belts that fed a third conveyer belt. One of the feeder belts fed coal and the other fed petcoke. The third belt, called the silo belt, fed the boilers.  The concentration of petcoke loaded to the boilers was controlled by the belt speed of each of the first two belts.

Additionally, the silo feed belt was designed to start empty and, as a result, was the last belt to be shut off so that it would be empty when stopped. The two feed belts were designed to be started empty or full.

The process of starting up the fuel feed system was to start the silo feed belt first, the coal feed belt second and the petcoke feed belt last. All belts were to be empty when started. The shutdown process required that the petcoke belt be shut down first, after it was empty. The Coal feed belt was to be shut down second, when it was empty.  The silo feed belt was to shut down last when it was empty.

The first step in the team’s analysis of the variation issues was to compare each shift’s start-up and shutdown processes. The Six Sigma Team did not take for granted that all shifts were compliant with the standardized start-up and shutdown processes, since the computer systems allowed them to change the order of startup and shut down.

What we found was that one of the four shifts shut down the coal and petcoke belts full, and then shut down the silo feed belt when empty. When starting the system up again, this shift would start the silo feed belt first and then both the coal and petcoke belts simultaneously. This shift had a low variation in petcoke concentration (within variation). Much lower, in fact, than all the shifts put together (between variation).

Another of the shifts would first shut down the petcoke feed belt full, then the coal belt full, then the silo belt when empty. On start-up they would start the silo feed belt first, then coal feed belt, then the petcoke feed. This group had the highest within variation in petcoke concentration, but still lower than the between variation of all the shifts put together.

The other two shifts followed the standardized process of start-up and shutdown. Their within variation in petcoke concentration was higher than the first shift, but lower than the second shift.

What the team had found, so far, was that two of the four shifts did not follow the standardized process of operation. Even so, the variation within each shift was within tolerance. The team then matched up emissions logs with the petcoke feed logs over a three week period. What they found was that the interaction of the different shifts created significant swings in petcoke concentration.  This “between” variation turned out to be the root cause of the variation problem.

The solution was to get all sifts to follow the same process. A team meeting with representatives of each shift resulted in an agreement to follow the first shift’s start-up and shutdown processes.  This became the standardized process for the plant’s fuel feed.

The Six Sigma team monitored the fuel feed process for four weeks after the agreement to measure the results. They found all shifts in compliance with the standardized process and a very low variation in petcoke concentration.  The low variation allowed the plant Operations group to incrementally increase the petcoke concentration and thereby reduce the plant’s operating cost.

One conclusion that the Six Sigma team made was that compliance with standardized processes is higher when the process owners were part of the dialog that creates the standardization. Processes are processes, but people are people. Processes are developed to serve the process owners (people) not the other way around.

Another conclusion was that communication between groups needed to be improved. The different groups need to understand why standardization is necessary and they need to know how to recover from unforeseen process upsets. In this case, what is the standardized process for start-up and shutdown when system maintenance required a different shutdown condition than normal? This latter situation required an expansion of the process management plan to include all pre start-up and per shutdown scenarios.

Variation Analysis

Posted on by
12

Variation

 First, remember that not all variation is bad. Planned variation, like that in an experiment, is a process improvement strategy. Unplanned variation, on the other hand, is nearly always bad.

 Two types of variation concern a process improvement team. These are common cause and special cause variation. All processes will have common cause variation. This variation is a normal part of the process (noise). It demonstrates the process’ true capability. Special cause variation on the other hand is not normal to the process. It is the result of exceptions in the process’ environment or inputs.

In a process improvement project, the first step is to eliminate special causes of variation and the second is to reduce common cause variation. Eliminating special causes of variation brings the process into a state of control and exposes the sources of common cause variation.

 Common Cause Variation

 Common cause variation is intrinsic to the process. It is random in nature and has predictable magnitude. Process noise is another name for it. An example would be the variation in your travel time to work everyday, with the absence of accidental, mechanical, or weather-related delays. When a process is expressing only common cause variation, its true capability for satisfying the customer is discernable. In this circumstance, the process is in control. Note that being in statistical control does not mean that the process is meeting customer expectations. The process could be precisely inaccurate.

 Continuing with the travel time example above, one source of common cause variation would be the typical ebb and flow of traffic on your route to work. Remember from the Define Phase that Y = f(x1 + x2 + … + xn). In the example, Y is the travel time and each x is an input that contributes to travel time; examples of x might include time of day or the day of week.

 Special Cause variation

 Special cause variation is the variation that is not a normal part of process noise. When special cause variation is present, it means that something about the process has changed. Special cause variation has a specific, identifiable cause. An example of special cause variation would be the effect of an accident or a mechanical problem on your travel time to work.

 Special cause variation is the first focus of process improvement efforts. When special cause variation exists, it is not possible to determine the process’ true capability to satisfy the customer. This is due to the effect that special cause variation has on inferences about central tendency (average) and standard deviation (spread in the data).

 Statisticians have developed specific control chart tests that describe the presence, timing, and behavior of various special cause variation components. These tests point out the impact of variation on the process’ output.

 Standard Deviation

 Process improvement teams use statistics to describe datasets and to make predictions about the future based on past events. Two important data characteristics used in descriptive statistics are standard deviation and central tendency (average, mean).

 Standard deviation is the measure of the dispersion or spread of a dataset. It is one of the more important parameters in statistical analysis. There are different ways to measure this parameter. Some of these are:

 Range: This is the difference between the largest and the smallest observation in a dataset. The range has a variety of uses, including the calculation of control chart control limits. In a normally distributed dataset, with no special cause variation, the range divided by six is an estimate of standard deviation. This is because 99 percent of the observations in a normally distributed dataset, with no special cause variation, fall within ±3 standard deviations from the mean. If the presence of special cause variation is unknown, divide the range by four. Th

Six Sigma Success and Honesty

Posted on by
3

Not all business problems lend themselves to the Six Sigma process improvement methodologies, especially those that have short time lines. There are many problems that business leadership understand and should just fix. A Six Sigma improvement project typically requires one to six months for a team to complete, depending upon the complexity and scope of the problem. This is longer than acceptable for some problems. In addition, many of the tools used in Six Sigma do not apply well to problems that are not process based. Examples of these would be emergencies and relationship issues. Process improvement tools apply better to up-front planning for these situations, than to the situations themselves.

Two other important considerations are the impact of variation and the truth. Not all variation is bad. Without variation, there would be no improvement. Six Sigma projects use variation to find both problems and solutions. This is because the awareness of a better way to do something manifests itself as variation. Consider, for example, that there are two processes producing an identical output. The operator of one process makes a change and introduces variation between the two processes. This new process produces fewer defects than the former process. Thus, by way of introducing variation, the operator discovers a better way to produce the output. Conversely, by eliminating all variation, we eliminate all experimentation, and as a result, we eliminate process improvement. The key is to plan and control variation. By planning and experimenting, a process owner can discover new and better ways to produce the product or service.

The truth is the basis of any effort to improve processes and eliminate defects. Sacred cows, sub-optimization, and parochialism are enemies of the truth and place limits upon how much improvement is achievable. To optimize improvement, we must embrace the truth, even if it hurts. The truth will literally set us free.